Diabetes mellitus is considered an epidemic of the 21st century, increasing dramatically in recent years, with a 9% global prevalence reported in 2014. The International Diabetes Federation estimates that 425 million people had diabetes in 2017, increasing to 629 million in 2045. The burden of increase is highest in LMICs compared with high-income countries (HICs). Diabetic retinopathy (DR) is a common microvascular complication of diabetes mellitus (types I and 2), which can lead to visual impairment and blindness if not detected early and treated. People with vision‐threatening DR have been shown to have increased risk of mental health issues, depression and loss of productivity.
DR is the leading cause of visual impairment and blindness in the working age population. DR is recognised by the World Health Organisation as a priority public health concern in LMICs. In HICs, DR Screening is conducted through systematic national-level programs, but LMICs are unlikely to have full population-based screening programmes owing to limited resources including technology and trained personnel. Screening programmes in HICs typically use retinal photography in community settings that are then graded by eyecare personnel. Potential cases of DR are then flagged for further clinical assessment or management.
By contrast, LMICs rely on opportunistic screening and case detection. A limited healthcare workforce is a major problem in most LMICs, with very few ophthalmologists to conduct ocular examinations. The reasons for the unavailability of DR Screening in LMIC settings are mostly attributed to the lack of skilled human resources, financial resources, geographical challenges, and evidence of what works in the local system. This project proposes to develop a cost effective computer-aided tool to detect DR at an early stage, prior to the occurrence of irreversible vision loss, using an appropriate set of features retrieved from retinal images (captured by a hand-held camera) along with Artificial Intelligence Deep Learning techniques.
Previous work has demonstrated that this system can be used by a non-specialist medical worker (with minimal training) in a range of environments (e.g., community clinic or patient’s home). Hand-held cameras are easy to transport, require little electrical power, and are user-friendly.
Three project stages will deliver the overarching project aim:
-Development of algorithms and AI system to effectively analyse retinal images with DR -Trial of system with Prof. Peto in UK grading centre to compare with conventional retinal photography and DR grading -Trial of system in the LMIC areas of Sri Lanka and India with established research partners This PhD can only be realised with the interdisciplinary connection of the ISRC, who bring expertise in current deep learning topics and computer vision algorithms, and existing partnership with the LMICs; while the Centre for Optometry and Vision Science academics bring expertise in retinal imaging, knowledge of extraction of key features from the retina, clinical management of DR, and partnership with Prof Tunde Peto. She is a world-recognised expert in the epidemiology of DR and is Head of the DR Screening programme in NI.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 7 February 2020
12:00AM
Interview Date
23 to 24 March 2020
Preferred student start date
mid September 2020
Telephone
Contact by phone
Email
Contact by email